Gateway agent cache and resource lifecycle leaks

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #11028 fix(gateway): close temporary agents after one-off tasks

  merged to main

  files: gateway/run.py, tests/gateway/test_background_command.py, tests/gateway/test_compress_command.py, tests/gateway/test_flush_memory_stale_guard.py, tests/gateway/test_session_hygiene.py

• #41974 fix(gateway): release evicted agent clients to stop RSS leak (#29298)

  merged to main

  files: gateway/run.py

  Show the diff

  • gateway/run.py

    @@ -12493,25 +12493,67 @@ async def _interrupt_and_clear_session(
                 self._release_running_agent_state(session_key)
     
         def _evict_cached_agent(self, session_key: str) -> None:
    -        """Remove a cached agent for a session (called on /new, /model, etc)."""
    +        """Remove a cached agent for a session (called on /new, /model, etc).
    +
    +        Pops the entry AND soft-releases the evicted agent's LLM client
    +        pool so the httpx connection (sockets + held buffers) is freed
    +        promptly rather than waiting on CPython GC — AIAgent holds
    +        reference cycles (callbacks, tool state) that delay refcount
    +        collection, so a manual release is required to keep gateway RSS
    +        flat across many /new, /model, undo and reset operations (#29298,
    +        same leak class as #25315).
    +
    +        The release is soft (``release_clients()``): it frees the client
    +        pool and per-turn child subagents but PRESERVES the session's
    +        terminal sandbox, browser daemon, and tracked bg processes (keyed
    +        on task_id), because the session may resume with a freshly-built
    +        agent.  Call sites that want a hard teardown (true conversation
    +        boundaries like /new) already call ``_cleanup_agent_resources``
    +        before evicting; ``release_clients`` is idempotent and safe to
    +        run again after that (the client is already None).
    +
    +        Cleanup runs on a daemon thread so we never block holding
    +        ``_agent_cache_lock`` on slow socket teardown — mirrors the
    +        cap-enforcer and idle-sweeper paths.
    +        """
             _lock = getattr(self, "_agent_cache_lock", None)
    +        evicted = None
             if _lock:
                 with _lock:
    -                entry = self._agent_cache.pop(session_key, None)
    -            # Release clients on a daemon thread, same as _enforce_agent_cache_cap.
    -            # Without this, every /new, /model, /reasoning, codex-runtime change,
    -            # and /undo leaked a full agent: OpenAI client, httpx transport, SSL
    -            # context, and conversation history. Only the /new path cleaned up
    -            # first; the rest popped the entry and dropped it on the floor.
    -            if entry is not None:
    -                agent = entry[0] if isinstance(entry, tuple) and entry else None
    -                if agent is not None:
    -                    threading.Thread(
    -                        target=self._release_evicted_agent_soft,
    -                        args=(agent,),
    -                        daemon=True,
    -                        name=f"agent-cache-cmd-evict-{session_key[:24]}",
    -                    ).start()
    +                evicted = self._agent_cache.pop(session_key, None)
    +        else:
    +            _cache = getattr(self, "_agent_cache", None)
    +            if _cache is not None:
    +                evicted = _cache.pop(session_key, None)
    +
    +        agent = evicted[0] if isinstance(evicted, tuple) and evicted else evicted
    +        if agent is None or agent is _AGENT_PENDING_SENTINEL:
    +            return
    +
    +        # Don't tear down an agent that's actively mid-turn — its client,
    +        # sandbox and child subagents are in use by the running request.
    +        running_ids = {
    +            id(a)
    +            for a in getattr(self, "_running_agents", {}).values()
    +            if a is not None and a is not _AGENT_PENDING_SENTINEL
    +        }
    +        if id(agent) in running_ids:
    +            return
    +
    +        try:
    +            threading.Thread(
    +                target=self._release_evicted_agent_soft,
    +                args=(agent,),
    +                daemon=True,
    +                name=f"agent-evict-{str(session_key)[:24]}",
    +            ).start()
    +        except Exception:
    +            # If we can't spawn a thread (interpreter shutdown), release
    +            # inline as a best-effort fallback.
    +            try:
    +                self._release_evicted_agent_soft(agent)
    +            except Exception:
    +                pass
     
         @staticmethod
         def _init_cached_agent_for_turn(agent: Any, interrupt_depth: int) -> None:

• #41975 fix(gateway): close residual memory-leak sites under heavy scheduled workload

  merged to main

  files: gateway/run.py, model_tools.py, tests/test_get_tool_definitions_cache_isolation.py

• #122925 fix(agent): close one-shot AIAgents on every exit path

  merged to main

  files: batch_runner.py, hermes_cli/cli_commands_mixin.py, plugins/platforms/feishu/feishu_comment.py, tests/test_agent_close_lifecycle.py, tui_gateway/methods_prompt.py